@agentvault/agentvault@0.23.40
The official **OpenClaw** plugin for AgentVault. Adds cryptographic identity, earned trust, and Signal-grade encrypted communications to OpenClaw agents. (Looking for a different framework? See **[Which Framework?](#which-framework)** below.)
AI Security Review
scanned 2mo ago · by lpm-firewall-aiNo automatic lifecycle attack or unrelated exfiltration was found, so blocking as malware is not supported. The explicit setup and runtime extension nevertheless create a dangerous agent-control and telemetry capability that warrants a warning.
Decision evidence
public snapshot- The explicit setup command installs and allow-lists an OpenClaw plugin, then writes channel settings through shell commands.
- Setup registers the OpenClaw gateway with pm2 and enables boot-time restart persistence.
- The loaded extension intercepts global HTTP activity and reports complete request URLs to its telemetry channel.
- Inbound AgentVault messages are marked command-authorized before being dispatched to the host agent.
- package.json has no npm preinstall, install, or postinstall hook.
- The installation, configuration, and persistence actions require an explicit setup command and invite token.
- The observed network service is the package's own AgentVault API; no unrelated exfiltration endpoint or self-dependency was found.
Source & flagged code
11 flaggedSource sends credentials or rich application records to a package-controlled external receiver enabled by default.
dist/cli.jsView on unpkg · L96This package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
dist/cli.jsView on unpkgFindings
Affected versions and remediation
This report applies to @agentvault/agentvault@0.23.40.
See all versions of @agentvault/agentvault for other recorded verdicts.
- Review the evidence and your use of @agentvault/agentvault@0.23.40 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.